
今天看到OpenAI的blog,主要讲解Evolution Strategies,然后顺着Andrej提供的简单实例,自己修改了一下用来求解CartPole-v0。几个有用的链接:
- Blog of Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Paper of Evolution Strategies as a Scalable Alternative to Reinforcement Learning
自己写的程序放在了这里。




近期评论